Manabu Ihara 研究室

主宰者：Manabu Ihara

東京工業大学

AI 要約（直近 5 年の研究成果）

Ihara研究室は、機械学習の手法を応用した材料・分子の物性予測と計算化学に関する研究を行っています。研究の中心は、化学組成や原子構造などの特徴量から材料の電子的性質や反応性を予測することです。ニューラルネットワークやガウス過程回帰などの機械学習手法を用いて、密度汎関数理論の計算結果を学習させ、より高速な予測モデルを構築しています。特に、訓練データが限定される場合の過学習を抑制し、少ないデータから正確に物性を予測する方法の開発に注力しています。研究では、高次元の特徴空間での機械学習特有の課題に取り組んでいます。具体的には、特徴空間の次元が高い場合に従来の機械学習手法がどのような限界に直面するか、ノイズや不均一性がある実験的な条件下でニューラルネットワークがどの程度の精度を保ち得るかを調査しています。また、ペロブスカイト太陽電池の電荷輸送層やポーラスシリコンなど、実際のエネルギーデバイスや太陽電池への応用を視野に入れた物性計算も行われています。さらに、カーボン/空気二次電池などの大容量エネルギー貯蔵システムの開発にも関与しており、機械学習を通じた物質設計と計算化学の融合による次世代エネルギー技術の実現を目指しています。

※ AI（Claude）が、公開されている論文要旨から研究の問い・手法・主要な発見を事実情報として抽出・再構成して自動生成しています。誤りを含む可能性があるため、正確性は研究室公式情報でご確認ください。

外部リンク

研究成果（37 件）

[2026] Gaussian Process Regression–Neural Network Hybrid with Optimized Redundant Coordinates: A New Simple Yet Potent Tool for Scientist's Machine Learning Toolbox
DOI: https://doi.org/10.1002/aidi.202500199
[2025] Neural networks for neurocomputing circuits: A computational study of tolerance to noise and activation function non-uniformity when machine learning materials properties
DOI: https://doi.org/10.1016/j.aichem.2025.100099
[2025] Effects of nonlinearity and inter-feature coupling in machine learning studies of Nb alloys with center-environment features
DOI: https://doi.org/10.20517/jmi.2025.05
[2025] A novel encoding method for high-dimensional categorical data for electricity demand forecasting in distributed energy systems
DOI: https://doi.org/10.1016/j.apenergy.2025.125989
[2025] Kernel regression methods for prediction of materials properties: Recent developments
DOI: https://doi.org/10.1063/5.0242118
[2025] Exploring the electronic properties of carbon nanoflake-based charge transport materials for perovskite solar cells: a computational study
DOI: https://doi.org/10.1039/d4cp04608k
[2024] Significantly Improved Stability of Carbon/Air Secondary Battery System By Separating Carbon Deposition Area
DOI: https://doi.org/10.1149/ma2024-02483400mtgabs
[2024] Concept and Advantages of Carbon/Air Secondary Battery System as a Fixed Compact Power Storage with Large Capacity
DOI: https://doi.org/10.1149/ma2024-02483469mtgabs
[2024] A machine-learned kinetic energy model for light weight metals and compounds of group III-V elements
DOI: https://doi.org/10.1088/2516-1075/ad7e8d
[2024] Computational Investigation of the Potential and Limitations of Machine Learning with Neural Network Circuits Based on Synaptic Transistors
DOI: https://doi.org/10.1021/acs.jpclett.4c01413

続きを表示（残り 27 件）

[2024] Natural-like generation of grain boundary models and the combined effects of microstructural elements and lithiation on the plastic behavior of TiO2: A computational study
DOI: https://doi.org/10.1016/j.commatsci.2024.112989
[2024] Machine learning of properties of lead-free perovskites with a neural network with additive kernel regression-based neuron activation functions
DOI: https://doi.org/10.1557/s43580-023-00749-1
[2024] Degeneration of kernel regression with Matern kernels into low-order polynomial regression in high dimension
DOI: https://doi.org/10.1063/5.0187867
[2024] Machine learning the screening factor in the soft bond valence approach for rapid crystal structure estimation
DOI: https://doi.org/10.1039/d4dd00152d
[2023] Machine learning of kinetic energy densities with target and feature smoothing: Better results with fewer training data
DOI: https://doi.org/10.1063/5.0175689
[2023] A controlled study of the effect of deviations from symmetry of the potential energy surface (PES) on the accuracy of the vibrational spectrum computed with collocation
DOI: https://doi.org/10.1063/5.0182373
[2023] Neural Network with Optimal Neuron Activation Functions Based on Additive Gaussian Process Regression
DOI: https://doi.org/10.1021/acs.jpca.3c02949
[2023] Orders-of-coupling representation achieved with a single neural network with optimal neuron activation functions and without nonlinear parameter optimization
DOI: https://doi.org/10.1016/j.aichem.2023.100013
[2023] Orders of coupling representations as a versatile framework for machine learning from sparse data in high-dimensional spaces
DOI: https://doi.org/10.1016/j.aichem.2023.100008
[2023] Hybrid Density Functional Tight Binding (DFTB)─Molecular Mechanics Approach for a Low-Cost Expansion of DFTB Applicability
DOI: https://doi.org/10.1021/acs.jctc.3c00310
[2023] Factors affecting the techno-economic and environmental performance of on-grid distributed hydrogen energy storage systems with solar panels
DOI: https://doi.org/10.1016/j.energy.2023.126736
[2023] The loss of the property of locality of the kernel in high-dimensional Gaussian process regression on the example of the fitting of molecular potential energy surfaces
DOI: https://doi.org/10.1063/5.0136156
[2023] Nano-scale smooth surface of the compact-TiO <sub>2</sub> layer <i>via</i> spray pyrolysis for controlling the grain size of the perovskite layer in perovskite solar cells
DOI: https://doi.org/10.1039/d3ra05547g
[2023] Clarifying the effects of nanoscale porosity of silicon on the bandgap and alignment: a combined molecular dynamics–density functional tight binding computational study
DOI: https://doi.org/10.1039/d3cp00633f
[2022] Investigation of expressive power of a neural network architecture suited for optical neural networks
DOI: https://doi.org/10.1117/12.2643705
[2022] Non-invasive improvement of machining by reversible electrochemical doping: A proof of principle with computational modeling on the example of lithiation of TiO2
DOI: https://doi.org/10.1016/j.matchemphys.2022.127183
[2022] Optimization of hyperparameters of Gaussian process regression with the help of а low-order high-dimensional model representation: application to a potential energy surface
DOI: https://doi.org/10.1007/s10910-022-01407-x
[2022] Advanced Machine Learning Methods for Learning from Sparse Data in High-Dimensional Spaces: A Perspective on Uses in the Upstream of Development of Novel Energy Technologies
DOI: https://doi.org/10.3390/physchem2020006
[2022] Effective passivation of TiO2/Si by interlayer SiOx controlled by scanning zone annealing for perovskite/Si tandem solar cell
DOI: https://doi.org/10.1016/j.solener.2022.03.056
[2022] Roadmap on Machine learning in electronic structure
DOI: https://doi.org/10.1088/2516-1075/ac572f
[2021] Easy construction of representations of multivariate functions with low-dimensional terms via Gaussian process regression kernel design
[2021] Random Sampling High Dimensional Model Representation Gaussian Process Regression (RS-HDMR-GPR) for representing multidimensional functions with machine-learned lower-dimensional terms allowing insight with a general method
DOI: https://doi.org/10.1016/j.cpc.2021.108220
[2021] Carbon/air secondary battery system and demonstration of its charge-discharge
DOI: https://doi.org/10.1016/j.jpowsour.2021.230681
[2021] Novel Electrode Evaluation Method for Pulse Jet Solid Oxide Fuel Cells using Liquid Hydrocarbon Fuels
DOI: https://doi.org/10.1149/1945-7111/ac15b6
[2021] Materials Design and Optimization for Next-Generation Solar Cell and Light-Emitting Technologies
DOI: https://doi.org/10.1021/acs.jpclett.1c00714
[2021] Nanostructure of Porous Si and Anodic SiO2 Surface Passivation for Improved Efficiency Porous Si Solar Cells
DOI: https://doi.org/10.3390/nano11020459
[2021] Modeling of plasmonic properties of nanostructures for next generation solar cells and beyond
DOI: https://doi.org/10.1080/23746149.2021.1908848

科研費（0 件）

まだデータがありません（KAKEN 取り込み後に表示）。

所属学会・役職（0 件）

まだデータがありません（学会データ連携後に表示）。

AI 要約（直近 5 年の研究成果）

外部リンク

関連研究室(8 件)

研究成果（37 件）

科研費（0 件）

所属学会・役職（0 件）